derp/TODO.md

derp - Backlog

Core

• Multi-server support (per-server config, shared plugins)
• Stable plugin API (versioned, breaking change policy)
• Paste overflow (auto-paste long output to FlaskPaste)
• URL shortener integration (shorten URLs in subscription announcements)
• Webhook listener (HTTP endpoint for push events to channels)
• Granular ACLs (per-command: trusted, operator, admin)

LLM Bridge

Goal: let an LLM agent interact with the bot over IRC in real-time, with full machine access (bash, file ops, etc.).

Architecture

Owner addresses the bot on IRC. A bridge daemon reads addressed messages, feeds them to an LLM with tool access, and writes replies back through the bot. The bot already has owner config ([bot] owner hostmask patterns) to gate who can trigger LLM interactions.

IRC -> bot stdout (addressed msgs) -> bridge -> LLM API -> bridge -> bot inbox -> IRC

Approach options (ranked)

1. Claude Code Agent SDK (clean, non-trivial)

   • Custom Python agent using anthropic SDK with tool_use
   • Define tools: bash exec, file read/write, web fetch
   • Persistent conversation memory across messages
   • Full control over the event loop -- real-time IRC is natural
   • Tradeoff: must implement and maintain tool definitions

2. Claude Code CLI per-message (simple, stateless)

   • echo "user said X" | claude --print --allowedTools bash,read,write
   • Each invocation is a cold start with no conversation memory
   • Simple to implement but slow startup, no multi-turn context
   • Could pass conversation history via system prompt (fragile)

3. Persistent Claude Code subprocess (hack, fragile)

   • Long-running claude process with stdin/stdout piped
   • Keeps context across messages within a session
   • Not designed for this -- output parsing is brittle
   • Session may drift or hit context limits

Bot-side plumbing needed

• --llm CLI flag: route logging to file, stdout for addressed msgs
• _is_addressed(): DM or nick-prefixed messages
• _is_owner(): only owner hostmasks trigger LLM routing
• Inbox file polling (/tmp/llm-inbox): bridge writes <target> <msg>
• llm-send script: line splitting (400 char), FlaskPaste overflow
• Stdout format: HH:MM [#chan] <nick> text / HH:MM --- status
• Only LLM-originated replies echoed to stdout (not all bot output)

Previous attempt (reverted)

The --llm mode was implemented and tested (commit ea6f079, reverted in 6f1f4b2). The stdout/stdin plumbing worked but Claude Code CLI cannot act as a real-time daemon -- each tool call is a blocking round-trip, making interactive IRC conversation impractical. The code is preserved in git history for reference.

Plugins -- Security/OSINT

• emailcheck -- SMTP VRFY/RCPT TO verification
• canary -- canary token generator/tracker
• virustotal -- hash/URL/IP/domain lookup (free API)
• abuseipdb -- IP abuse confidence scoring (free tier)
• jwt -- decode tokens, show claims/expiry, flag weaknesses
• mac -- OUI vendor lookup (local IEEE database)
• pastemoni -- monitor paste sites for keywords
• internetdb -- Shodan InternetDB host recon (free, no API key)

Plugins -- Utility

• paste -- manual paste to FlaskPaste
• shorten -- manual URL shortening
• cron -- scheduled bot commands on a timer

Teams

• Microsoft Teams adapter via outgoing webhooks
• TeamsBot + TeamsMessage (duck-typed with IRC Message)
• HMAC-SHA256 webhook validation
• Permission tiers via AAD object IDs
• Route send() through SOCKS5 proxy (bug fix)
• Adaptive Cards for richer formatting
• Graph API integration for DMs
• Teams event handlers (member join/leave)

Telegram

• Telegram adapter via long-polling (no SDK)
• TelegramBot + TelegramMessage (duck-typed with IRC Message)
• All HTTP through SOCKS5 proxy
• Message splitting at 4096-char limit
• @botusername suffix stripping in groups
• Permission tiers via user IDs
• Inline keyboard support for interactive replies
• Markdown/HTML formatting mode toggle
• Webhook mode (for setWebhook instead of getUpdates)

Discord

• Discord adapter via WebSocket gateway + REST API (no SDK)
• DiscordBot + DiscordMessage (duck-typed with IRC Message)
• Gateway intents for message content
• Message splitting at 2000-char limit
• Permission tiers via user/role IDs
• Slash command registration (optional)

Matrix

• Matrix adapter via long-poll /sync endpoint (no SDK)
• MatrixBot + MatrixMessage (duck-typed with IRC Message)
• Room-based messaging (rooms map to channels)
• Power levels map to permission tiers
• E2EE support (optional, requires libolm)

XMPP

• XMPP adapter via persistent TCP + XML stanzas (no SDK)
• XMPPBot + XMPPMessage (duck-typed with IRC Message)
• MUC (Multi-User Chat) support -- rooms map to channels
• SASL authentication
• TLS/STARTTLS connection

Mumble

• Mumble adapter via TCP/TLS + protobuf control channel (no SDK)
• MumbleBot + MumbleMessage (duck-typed with IRC Message)
• Text chat only (no voice)
• Channel-based messaging
• Minimal protobuf encoder/decoder (no protobuf dep)

Slack

• Slack adapter via Socket Mode WebSocket (no SDK)
• SlackBot + SlackMessage (duck-typed with IRC Message)
• OAuth token + WebSocket for events
• Channel/DM messaging
• Permission tiers via user IDs

Mattermost

• Mattermost adapter via WebSocket API (no SDK)
• MattermostBot + MattermostMessage (duck-typed with IRC Message)
• Self-hosted Slack alternative
• Channel/DM messaging

Bluesky

• Bluesky adapter via AT Protocol firehose + REST API (no SDK)
• BlueskyBot + BlueskyMessage (duck-typed with IRC Message)
• Mention-based command dispatch
• Post/reply via com.atproto.repo.createRecord

Testing

• Plugin command unit tests (encode, hash, dns, cidr, defang)
• CI pipeline (Gitea Actions)